© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12173
    Prev
    Next
    INDEX
    Explanations

    terms related to reservations and reserved rights in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "reserve" or variations of it

    np_acts-logits-general · gemini-2.0-flash

    reserve or reserved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tode
    -0.47
    fæ
    -0.46
     Broughton
    -0.44
    impianto
    -0.43
    CURL
    -0.43
     <<<<<<<<<<<<<<
    -0.42
    Zy
    -0.42
     Đi
    -0.42
    fahr
    -0.41
    uomo
    -0.41
    POSITIVE LOGITS
     reserve
    2.42
     Reserve
    2.14
    Reserve
    2.09
    reserve
    2.05
     RESERVE
    2.00
     reserves
    1.94
     reserved
    1.92
     Reserved
    1.82
     Reserves
    1.81
     reserving
    1.78
    Activations Density 0.154%

    No Known Activations